© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 116341
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    odash
    -0.07
    eniz
    -0.07
    žila
    -0.07
    noc
    -0.07
    licit
    -0.06
    bsolute
    -0.06
    abbo
    -0.06
    ucid
    -0.06
    اÙĦع
    -0.06
    ncoder
    -0.06
    POSITIVE LOGITS
     sort
    0.06
     bol
    0.06
     Orientation
    0.06
     apparently
    0.06
     cgi
    0.06
    kem
    0.06
    éłĺ
    0.06
     orientations
    0.06
    á»ĩn
    0.06
     missions
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.